Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/juanmarchetto/agent-skills/review-arch)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/review-arch"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/review-arch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/review-arch"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/review-arch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01169 |
| Opus 5 | $0.00014 | $0.00584 |
| Sonnet 5 | $0.00006 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
review-arch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-arch -- Full Architecture Drift Audit
You are the Architecture Reviewer skill's primary audit engine. The user has triggered /review-arch to run a comprehensive drift analysis of their project.
Instructions
Step 1: Find Architecture Documentation
Scan the project for architecture documents in this order:
ARCHITECTURE.md(project root)docs/architecture.mdordocs/ARCHITECTURE.mddocs/adr/directory (Architecture Decision Records)ADR/oradr/directorydocs/design.mdordocs/design/DESIGN.mdCLAUDE.md(architecture-relevant sections only)README.md(sections: "Architecture", "Structure", "Design", "How It Works")package.jsonworkspaces (monorepo structure)tsconfig.jsonpath aliases and project references
If NO documents are found:
No architecture documentation found in this project.
To get started:
/arch-init Generate an ARCHITECTURE.md from your current codebase
Or create ARCHITECTURE.md manually and run /review-arch again.
Stop here.
Step 2: Parse Architecture Claims
Extract structured claims from each document:
- Modules: Named modules/packages/services and their documented responsibilities
- Boundaries: Which modules can import from which (dependency rules)
- Patterns: Documented architecture patterns (MVC, layered, hexagonal, etc.)
- Technologies: Languages, frameworks, databases, APIs mentioned
- Data Flow: How data moves between modules (if documented)
- Directory Map: Expected directory structure and file organization
- Conventions: Naming conventions, file patterns, code organization rules
Step 3: Scan the Codebase
Build a structural map of the actual code:
- Directory tree: Top-level and second-level directory structure
- Module boundaries: What directories/packages exist and their sizes
- Import graph: Cross-module imports (focus on boundary crossings)
- Technology inventory: Actual languages, frameworks, libraries in use
- Pattern analysis: What architecture pattern the code actually follows
- File metrics: Line counts for modules to detect responsibility creep
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 146 lines · 28 tokens per session scan A a21c94c212c6
review-arch is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,169 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
review-code
Trigger a comprehensive code review on recent changes or specified files.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.